License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.COSIT.2022.16
URN: urn:nbn:de:0030-drops-169013
URL: https://drops.dagstuhl.de/opus/volltexte/2022/16901/
Go to the corresponding LIPIcs Volume Portal


De Cock, Laure ; Verstockt, Steven ; Vandeviver, Christophe ; Van de Weghe, Nico

Smart Crowd Management: The Data, the Users and the Solution (Short Paper)

pdf-format:
LIPIcs-COSIT-2022-16.pdf (1 MB)


Abstract

This research project is situated in the domain of smart crowd management, a domain that is gaining importance because of the challenges that arise from urbanization, but also the opportunities that come with smart cities. While our cities become more crowded every day, they also become smarter, for example by employing pedestrian tracking sensors. However, the datasets that are generated by these sensors do not allow smart crowd management yet, because they are sparse and not linked to the perception of the crowd. This research will tackle these issues in three steps. First, pedestrian counts will be estimated on streets that have no tracking data by use of deep learning and space syntax data. Next, the perception of crowdedness within the crowd will be linked to the objective pedestrian counts by conducting two user studies, and finally, the resulting subjective pedestrian counts will be used as weights for a routing algorithm. The last step has already been developed as a proof of concept. The routing algorithm, that uses partly simulated data and partly real-time tracking data, has been embedded in a webtool to show stakeholders the potential and goal of this innovative project.

BibTeX - Entry

@InProceedings{decock_et_al:LIPIcs.COSIT.2022.16,
  author =	{De Cock, Laure and Verstockt, Steven and Vandeviver, Christophe and Van de Weghe, Nico},
  title =	{{Smart Crowd Management: The Data, the Users and the Solution}},
  booktitle =	{15th International Conference on Spatial Information Theory (COSIT 2022)},
  pages =	{16:1--16:7},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-257-0},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{240},
  editor =	{Ishikawa, Toru and Fabrikant, Sara Irina and Winter, Stephan},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2022/16901},
  URN =		{urn:nbn:de:0030-drops-169013},
  doi =		{10.4230/LIPIcs.COSIT.2022.16},
  annote =	{Keywords: crowd tracking, crowd modeling, space syntax, deep learning, perception, routing}
}

Keywords: crowd tracking, crowd modeling, space syntax, deep learning, perception, routing
Collection: 15th International Conference on Spatial Information Theory (COSIT 2022)
Issue Date: 2022
Date of publication: 22.08.2022
Supplementary Material: Software (Source Code): https://github.com/laudcock/Smart_crowd_management


DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI